cardTitle = mergeStringContent(environment) card = createSanitizedCard(cardCategory, cardTitle, cardLink) cards.append(card) postSize = len(cards) print("added " + str(postSize - preSize) + " cards for category : " + cardCategory) if __name__ == '__main__': print("Make sure Firefox is running !") cards = [] # the timeout argument in the constructor may have to be increased - if errors occur timeout = 1 browser = ContentRetrieverUsingSelenium(timeout) try: createGeneralCards(cards, browser, ['h3', 'h2'], 'https://golang.org/doc/install', 'Getting Started') addTourCards(cards, browser) createGeneralCards(cards, browser, ['h3', 'h2'], 'https://golang.org/ref/mem', 'The Go Memory Model') createGeneralCards(cards, browser, ['h3', 'h2'], 'https://golang.org/doc/code.html', 'How to Write Go Code') createGeneralCards(cards, browser, ['h3', 'h2'], 'https://golang.org/doc/effective_go.html', 'Effective Go') createGeneralCards(cards, browser, ['h3', 'h2'], 'https://golang.org/doc/faq',
cardLink = url + "#" + linkId cardTitle = mergeStringContent(environment) card = createSanitizedCard(cardCategory, cardTitle, cardLink) cards.append(card) postSize = len(cards) print("added " + str(postSize - preSize) + " cards for category : " + cardCategory) if __name__ == "__main__": print("Make sure Firefox is running !") cards = [] # the timeout argument in the constructor may have to be increased - if errors occur timeout = 1 browser = ContentRetrieverUsingSelenium(timeout) try: createGeneralCards(cards, browser, ["h3", "h2"], "https://golang.org/doc/install", "Getting Started") addTourCards(cards, browser) createGeneralCards(cards, browser, ["h3", "h2"], "https://golang.org/ref/mem", "The Go Memory Model") createGeneralCards(cards, browser, ["h3", "h2"], "https://golang.org/doc/code.html", "How to Write Go Code") createGeneralCards(cards, browser, ["h3", "h2"], "https://golang.org/doc/effective_go.html", "Effective Go") createGeneralCards(cards, browser, ["h3", "h2"], "https://golang.org/doc/faq", "Frequently Asked Questions") finally: browser.close() createCSVFile("golang", cards)
from ankiflashcardcreationtools.CrawlTools import ContentRetrieverUsingSelenium, mergeStringContent from ankiflashcardcreationtools.CardTools import createSanitizedCard, createCSVFile if __name__ == "__main__": print("Make sure Firefox is running !") cards = [] timeout = 1.5 baseUrl = "https://docs.python.org/3/tutorial/" startUrl = baseUrl + "index.html" cardCategory = "Python 3" browser = ContentRetrieverUsingSelenium(timeout) try: _, content = browser.getContentOfPage(startUrl) tocTree = content.find("div", {"class": "toctree-wrapper"}) links = tocTree.find_all("a", {"class": "reference internal"}) for link in links: cardTitle = mergeStringContent(link) cardLink = baseUrl + link.attrs["href"] card = createSanitizedCard(cardCategory, cardTitle, cardLink) cards.append(card) finally: browser.close() print("finished collecting " + str(len(cards))) createCSVFile("python3", cards)
from ankiflashcardcreationtools.CrawlTools import ContentRetrieverUsingSelenium,\ mergeStringContent from ankiflashcardcreationtools.CardTools import createSanitizedCard,\ createCSVFile if __name__ == '__main__': print("Make sure Firefox is running !") cards = [] timeout = 1.5 baseUrl = 'https://docs.python.org/3/tutorial/' startUrl = baseUrl + 'index.html' cardCategory = 'Python 3' browser = ContentRetrieverUsingSelenium(timeout) try: _, content = browser.getContentOfPage(startUrl) tocTree = content.find('div', {'class': 'toctree-wrapper'}) links = tocTree.find_all('a', {'class': 'reference internal'}) for link in links: cardTitle = mergeStringContent(link) cardLink = baseUrl + link.attrs['href'] card = createSanitizedCard(cardCategory, cardTitle, cardLink) cards.append(card) finally: browser.close() print("finished collecting " + str(len(cards))) createCSVFile("python3", cards)